I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
9
,
No
.
3
,
Ma
r
ch
2
0
1
8
,
p
p
.
764
~
770
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs.v
9
.
i3
.
p
p
7
6
4
-
770
764
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
An Non
Destru
cti
v
e Test
f
o
r
t
he
De
tect
io
n
o
f
Wel
d D
efec
ts
Using
I
m
a
g
e
Proc
ess
ing
V.
K
a
la
is
elv
i,
D.
J
o
hn
Ara
v
i
nd
ha
r
Re
se
a
rc
h
S
c
h
o
lar,
CS
E
De
p
a
rtm
e
n
t,
Hi
n
d
u
sta
n
Un
iv
e
rsit
y
,
Ke
la
m
b
a
k
a
m
,
Ch
e
n
n
a
i,
T
a
m
il
Na
d
u
6
0
3
1
0
3
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
h
is
to
r
y:
R
ec
eiv
ed
Sep
9
,
2
0
1
7
R
ev
i
s
ed
Dec
2
0
,
2
0
1
7
A
cc
ep
ted
J
an
7
,
2
0
1
8
W
e
ld
in
g
is
a
f
a
b
rica
ti
o
n
o
f
jo
in
in
g
m
a
teria
ls
in
to
o
n
e
c
o
m
p
o
n
e
n
t.
De
fe
c
ts
a
r
e
u
n
a
v
o
id
a
b
le
d
u
ri
n
g
th
e
w
e
ld
in
g
p
ro
c
e
ss
,
a
n
d
h
e
n
c
e
th
e
in
sp
e
c
ti
o
n
o
f
w
e
ld
s
is
a
m
o
st
i
m
p
o
rtan
t
tas
k
in
m
a
n
y
i
n
d
u
str
ies
.
In
th
is
w
o
rk
,
a
Co
m
p
u
ter
A
id
e
d
De
tec
ti
o
n
(CA
D)
s
y
ste
m
is
d
e
sig
n
e
d
t
o
d
e
tec
t
w
e
ld
d
e
f
e
c
ts
b
a
se
d
o
n
im
a
g
e
p
ro
c
e
ss
in
g
tec
h
n
iq
u
e
s.
It
is
a
n
o
n
-
d
e
stru
c
ti
v
e
tes
ti
n
g
w
h
ich
u
se
s
X
-
ra
y
im
a
g
e
s.
T
h
e
p
ro
p
o
se
d
sy
ste
m
m
a
in
ly
c
o
n
sists
o
f
th
re
e
sta
g
e
s;
g
ra
d
i
e
n
t
im
a
g
e
f
o
r
m
a
ti
o
n
,
f
il
tratio
n
b
y
G
a
u
ss
ian
p
y
ra
m
id
a
l
f
il
ters
a
lg
o
r
it
h
m
a
n
d
se
g
m
e
n
tatio
n
b
y
Ex
p
e
c
tatio
n
a
n
d
M
a
x
im
i
z
a
ti
o
n
(EM
)
a
lg
o
rit
h
m
.
In
th
is
stu
d
y
,
GD
X
-
ra
y
we
ld
ima
g
e
d
a
tab
a
se
is
u
se
d
to
e
v
a
lu
a
te
th
e
p
ro
p
o
se
d
s
y
ste
m
.
T
h
e
p
e
rf
o
r
m
a
n
c
e
a
n
a
l
y
sis
o
f
th
e
p
r
o
p
o
se
d
sy
ste
m
is
d
o
n
e
b
y
m
e
a
su
rin
g
th
e
se
n
siti
v
it
y
,
sp
e
c
i
f
i
c
it
y
,
a
n
d
a
c
c
u
ra
c
y
o
f
th
e
se
g
m
e
n
ted
im
a
g
e
w
it
h
th
e
h
e
lp
o
f
it
s co
rre
sp
o
n
d
in
g
g
ro
u
n
d
tr
u
th
im
a
g
e
s.
K
ey
w
o
r
d
s
:
C
A
D
E
M
alg
o
r
ith
m
I
m
ag
e
Se
g
m
e
n
tatio
n
Gau
s
s
ia
n
Fil
ter
X
-
r
a
y
W
eld
d
ef
ec
ts
Co
p
y
rig
h
t
©
201
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
V.
Kala
is
el
v
i
R
esear
ch
Sch
o
lar
,
C
SE
Dep
ar
t
m
en
t
,
Hin
d
u
s
ta
n
Un
i
v
er
s
i
t
y
,
Kela
m
b
ak
a
m
,
C
h
e
n
n
ai,
T
am
il
Nad
u
6
0
3
1
0
3
,
I
n
d
ia
E
m
ail
:
v
k
a
lais
e
lv
i@red
i
ffm
a
il
.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
d
etec
tio
n
o
f
w
eld
i
n
g
d
ef
ec
ts
is
a
m
aj
o
r
co
n
ce
r
n
in
a
n
y
i
n
d
u
s
tr
ial
p
r
o
d
u
ctiv
i
t
y
u
n
it.
Gen
er
all
y
,
th
e
w
eld
i
n
g
q
u
alit
y
d
ep
en
d
s
u
p
o
n
th
e
v
o
ltag
e,
cu
r
r
en
t,
w
eld
in
g
d
u
r
atio
n
an
d
m
o
s
t
i
m
p
o
r
ta
n
tl
y
t
h
e
elec
tr
o
d
es
q
u
alit
y
th
at
ar
e
u
s
ed
f
o
r
w
eld
in
g
.
X
-
r
a
y
r
ad
io
g
r
ap
h
y
is
t
h
e
w
id
el
y
u
s
ed
to
d
etec
t
w
eld
d
ef
ec
ts
.
So
m
e
o
f
th
e
w
eld
d
ef
ec
t d
etec
tio
n
an
d
s
e
g
m
en
tatio
n
m
et
h
o
d
s
ar
e
d
is
cu
s
s
ed
in
th
i
s
s
ec
tio
n
.
1
.
1
B
a
ck
g
ro
un
d
T
h
e
s
eg
m
e
n
tatio
n
o
f
r
ef
lec
ted
laser
lin
es
i
n
r
o
b
o
tic
ar
c
w
e
ld
in
g
i
s
d
escr
ib
ed
in
[
1
]
.
T
h
e
2
D
in
te
n
s
it
y
d
is
tr
ib
u
tio
n
i
s
m
o
d
eled
to
d
etec
t
th
e
r
ef
lec
ted
laser
lin
e.
I
t
co
n
s
is
t
s
o
f
t
h
r
ee
ef
f
ec
ti
v
e
m
eth
o
d
s
;
s
p
lin
e
en
h
a
n
ce
m
en
t,
g
r
ad
ie
n
t
d
etec
ti
o
n
f
ilter
,
an
d
th
r
es
h
o
ld
ap
p
r
o
ac
h
.
So
m
e
o
f
t
h
e
m
aj
o
r
d
ef
ec
ts
li
k
e
s
m
a
ll
c
h
ip
s
b
u
r
r
o
r
d
ir
t
th
at
ca
u
s
es
t
h
e
d
ef
ec
ts
in
t
h
e
w
eld
ed
s
p
o
ts
ar
e
d
i
s
cu
s
s
ed
in
[
2
]
.
Fo
r
th
e
d
etec
tio
n
o
f
th
ese
d
e
f
ec
ts
,
alg
o
r
ith
m
s
li
k
e
Ho
u
g
h
cir
cle
d
etec
tio
n
an
d
co
lo
u
r
s
eg
m
e
n
t
atio
n
m
eth
o
d
s
ar
e
u
s
ed
.
A
l
s
o
,
b
y
co
m
b
i
n
in
g
t
h
e
alg
o
r
ith
m
s
li
k
e
m
o
r
p
h
o
lo
g
ic
al
an
d
cir
cle
d
etec
tio
n
alg
o
r
ith
m
s
i
n
th
e
v
i
s
io
n
s
y
s
te
m
,
th
e
f
au
l
ts
ca
n
b
e
id
en
ti
f
ied
.
An
a
u
to
m
at
ic
w
eld
d
ef
ec
t
s
eg
m
e
n
tatio
n
s
y
s
te
m
b
ased
o
n
a
m
u
lt
i
-
s
tep
r
ad
io
g
r
ap
h
ic
i
m
a
g
e
en
h
a
n
ce
m
en
t
alg
o
r
it
h
m
i
s
d
is
cu
s
s
ed
in
[
3
]
.
A
t
f
ir
s
t,
en
h
a
n
c
e
m
en
t
is
p
er
f
o
r
m
ed
b
y
li
n
ea
r
w
ei
g
h
ti
n
g
b
et
w
ee
n
th
e
co
n
tr
ast
li
m
ite
d
ad
ap
tiv
e
h
is
to
g
r
a
m
eq
u
aliza
tio
n
i
m
a
g
e
an
d
th
e
o
r
ig
i
n
al
r
ad
io
g
r
ap
h
i
c
i
m
ag
e
s
.
T
h
en
t
h
e
an
is
o
tr
o
p
ic
d
if
f
u
s
io
n
f
ilter
in
g
is
u
s
ed
f
o
r
s
m
o
o
t
h
in
g
,
a
n
d
as
a
f
i
n
al
s
tep
,
th
e
f
u
zz
y
en
h
a
n
c
e
m
en
t
al
g
o
r
ith
m
i
s
u
s
ed
f
o
r
f
ilter
i
n
g
th
e
i
m
ag
e
s
.
An
a
u
to
m
atic
s
y
s
te
m
f
o
r
t
h
e
ex
tr
ac
tio
n
o
f
d
e
f
ec
ts
f
r
o
m
t
h
e
r
ad
io
g
r
ap
h
ic
w
eld
i
m
a
g
es
is
d
is
c
u
s
s
ed
in
[
4
]
.
A
t
f
ir
s
t,
th
e
w
eld
i
m
ag
e
s
ar
e
p
r
e
-
p
r
o
ce
s
s
ed
to
in
cr
ea
s
e
th
e
q
u
alit
y
o
f
th
e
i
m
a
g
e,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
A
n
N
o
n
Destr
u
ctive
Tes
t
f
o
r
t
h
e
Dete
ct
io
n
o
f W
eld
Defe
cts
…
(
V
.
K
a
la
is
elvi
)
765
an
d
th
e
n
F
u
zz
y
C
Me
a
n
s
(
FC
M)
s
eg
m
e
n
tatio
n
a
lg
o
r
it
h
m
is
u
s
ed
to
d
etec
t
w
eld
d
ef
ec
t
s
f
r
o
m
w
h
ic
h
t
h
e
3
D
co
n
to
u
r
p
lo
ts
ar
e
p
lo
tted
b
y
u
s
in
g
t
h
e
e
x
tr
ac
ted
f
ea
t
u
r
es.
A
m
o
d
if
ied
b
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
m
et
h
o
d
f
o
r
r
ea
l
-
t
i
m
e
w
eld
d
ef
ec
t
d
etec
t
io
n
al
g
o
r
ith
m
i
s
d
is
cu
s
s
ed
i
n
[
5
]
.
I
t
is
b
ased
o
n
t
h
e
as
s
u
m
p
tio
n
t
h
at
th
e
p
ix
el
in
te
n
s
ities
o
f
th
e
b
ac
k
g
r
o
u
n
d
i
n
a
n
i
m
a
g
e
s
eq
u
en
ce
ar
e
f
i
x
ed
.
T
h
e
w
eld
d
ef
ec
ts
ar
e
d
etec
ted
b
ased
o
n
th
e
d
i
s
tr
ib
u
tio
n
o
f
b
ac
k
g
r
o
u
n
d
p
ix
el
s
t
h
at
f
o
llo
ws
a
Gau
s
s
ia
n
d
is
tr
ib
u
tio
n
w
it
h
m
ax
i
m
u
m
p
r
o
b
ab
ilit
y
.
T
h
e
s
eg
m
e
n
tatio
n
ap
p
r
o
ac
h
es
ar
e
co
m
p
ar
ed
an
d
ev
alu
a
ted
in
[
6
]
f
o
r
w
e
ld
d
ef
e
ct
i
m
a
g
es.
T
h
e
id
e
n
ti
f
ied
d
ef
e
cts
ar
e
co
m
p
ar
ed
w
it
h
id
ea
l
s
e
g
m
e
n
tat
io
n
m
ap
in
ter
m
s
o
f
m
i
s
s
-
s
e
g
m
en
ted
p
ix
el
s
lik
e
co
m
p
ac
t
n
es
s
,
lo
ca
tio
n
,
a
n
d
co
n
n
ec
ti
v
it
y
.
A
m
e
th
o
d
f
o
r
th
e
id
en
tific
atio
n
o
f
t
h
e
lo
ca
tio
n
o
f
t
h
e
la
s
er
s
t
r
ip
o
n
a
w
e
ld
s
ea
m
tr
ac
k
i
n
g
is
ex
p
lai
n
ed
in
[
7
]
.
I
t
is
d
o
n
e
b
y
ap
p
l
y
i
n
g
t
h
e
R
ad
o
n
tr
an
s
f
o
r
m
a
n
d
also
p
r
eser
v
es
t
h
e
i
n
f
o
r
m
atio
n
o
f
t
h
e
laser
s
tr
ip
e.
T
h
en
th
e
in
v
er
s
e
R
ad
o
n
tr
an
s
f
o
r
m
is
ap
p
lied
s
o
th
at
th
e
n
o
i
s
es
ar
e
r
em
o
v
ed
.
A
t
la
s
t,
th
e
g
r
o
o
v
e
ar
ea
s
ar
e
s
eg
m
e
n
ted
b
y
t
h
e
i
m
p
r
o
v
ed
f
ast
F
C
M
cl
u
s
ter
i
n
g
al
g
o
r
ith
m
.
A
n
i
m
p
r
o
v
ed
Ots
u
2
D
i
m
ag
e
s
eg
m
e
n
tatio
n
alg
o
r
ith
m
f
o
r
th
e
r
eq
u
ir
e
m
e
n
t
o
f
t
h
e
u
n
d
er
w
ater
w
eld
i
n
g
V
-
s
ea
m
tr
ac
k
i
n
g
is
d
is
c
u
s
s
ed
i
n
[
8
]
.
T
h
e
alg
o
r
ith
m
m
ak
e
s
a
d
is
cr
i
m
i
n
ate
c
h
an
g
e
in
a
d
o
m
ai
n
p
ar
titi
o
n
o
f
th
e
2
D
h
is
to
g
r
a
m
b
y
ad
d
in
g
a
r
elev
an
t
v
ar
iab
le.
A
d
d
itio
n
a
l
l
y
,
a
n
o
p
ti
m
al
t
h
r
es
h
o
ld
in
g
is
o
b
tain
ed
b
y
e
n
lar
g
i
n
g
t
h
e
s
ea
r
c
h
s
tep
o
f
t
h
e
th
r
es
h
o
ld
in
g
.
A
m
et
h
o
d
o
f
s
e
g
m
en
tin
g
t
h
e
s
ec
o
n
d
ca
teg
o
r
y
o
f
d
ef
ec
ts
i
n
th
e
w
eld
i
n
g
j
o
in
t
s
is
d
i
s
cu
s
s
e
d
in
[
9
]
.
I
t
m
ak
e
s
u
s
e
o
f
t
h
e
d
ig
i
tized
r
ad
io
g
r
ap
h
ic
i
m
a
g
e
i
n
ca
s
e
o
f
l
o
w
o
r
n
o
is
y
co
n
tr
ast
i
m
a
g
es.
T
h
e
co
m
b
i
n
atio
n
o
f
th
e
co
n
tr
a
s
t
en
h
a
n
ce
m
en
t
s
,
h
is
to
g
r
a
m
eq
u
aliza
tio
n
,
an
d
i
m
a
g
e
th
r
e
s
h
o
ld
i
n
g
p
r
o
ce
s
s
e
s
ar
e
u
s
ed
f
o
r
th
e
s
eg
m
e
n
tatio
n
o
f
d
e
f
ec
ts
.
A
s
e
g
m
e
n
tat
io
n
m
et
h
o
d
f
o
r
t
h
e
id
e
n
ti
f
icatio
n
o
f
d
ef
ec
t
s
i
n
t
h
e
X
-
r
ay
w
eld
i
m
a
g
es
is
d
is
cu
s
s
ed
in
[
1
0
]
.
A
s
th
e
X
-
r
a
y
w
eld
i
m
ag
e
s
ar
e
o
f
l
o
w
-
co
n
tr
ast
an
d
n
o
is
y
i
n
n
atu
r
e,
th
e
d
ig
it
ized
r
ad
io
g
r
ap
h
ic
w
eld
i
m
a
g
es
ar
e
u
s
ed
f
o
r
t
h
e
s
e
g
m
e
n
tat
io
n
.
I
t
i
s
m
ai
n
l
y
b
ased
o
n
a
th
r
e
s
h
o
ld
in
g
m
et
h
o
d
k
n
o
w
n
as
m
u
ltip
le
t
h
r
es
h
o
ld
in
g
alo
n
g
w
it
h
t
h
e
s
u
p
p
o
r
t v
ec
to
r
m
ac
h
i
n
e
alg
o
r
it
h
m
.
A
s
e
g
m
en
tatio
n
m
eth
o
d
u
s
ed
to
d
etec
t
th
e
d
ef
ec
ts
o
n
th
e
w
eld
ed
s
u
r
f
ac
e
is
d
is
cu
s
s
ed
in
[
1
1
]
.
T
h
e
d
ef
ec
ts
ar
e
s
m
a
ller
in
s
ize
a
n
d
s
h
ap
e
a
n
d
also
h
a
v
e
lo
w
co
n
t
r
ast
lev
e
l
ch
ar
ac
ter
i
s
tics
w
h
ic
h
ar
e
ca
u
s
ed
d
u
e
to
th
e
n
o
n
-
u
n
i
f
o
r
m
il
lu
m
i
n
atio
n
s
.
I
t
u
s
es
lev
el
s
et
ac
ti
v
e
co
n
to
u
r
alg
o
r
it
h
m
in
w
h
ic
h
t
h
e
ce
n
t
r
e
-
s
u
r
r
o
u
n
d
f
ea
tu
r
e
s
alien
c
y
m
ap
is
u
s
ed
to
r
ed
u
ce
th
e
clu
s
ter
i
n
g
b
ac
k
g
r
o
u
n
d
.
A
m
ac
h
i
n
e
v
is
io
n
w
eld
i
n
g
r
o
b
o
t
f
o
r
L
E
D
f
ila
m
en
t
w
eld
i
n
g
is
d
esi
g
n
ed
in
[
1
2
]
.
I
t
u
s
e
s
i
m
ag
e
s
eg
m
e
n
tatio
n
alg
o
r
ith
m
li
k
e
g
r
e
y
le
v
el
tr
an
s
f
o
r
m
atio
n
,
ed
g
e
d
etec
tio
n
,
an
d
t
w
o
v
al
u
e
tr
an
s
f
o
r
m
atio
n
f
o
r
p
r
o
ce
s
s
in
g
t
h
e
s
eg
m
e
n
tat
io
n
p
r
o
ce
d
u
r
es.
A
m
eth
o
d
o
f
co
lo
r
im
a
g
e
s
eg
m
en
tatio
n
u
s
i
n
g
j
o
in
t
co
lo
r
te
x
tu
r
e
h
is
to
g
r
a
m
b
ased
o
n
r
eg
i
o
n
m
er
g
i
n
g
alg
o
r
ith
m
i
s
d
is
c
u
s
s
ed
i
n
[
1
3
]
.
I
t
u
s
es
b
o
t
h
th
e
in
f
o
r
m
at
io
n
o
f
tex
t
u
r
e
h
is
to
g
r
a
m
a
n
d
th
e
c
o
lo
r
h
is
to
g
r
a
m
f
o
r
m
ea
s
u
r
in
g
th
e
s
i
m
ilar
it
ies
o
f
v
ar
io
u
s
r
eg
io
n
s
a
n
d
to
g
u
id
e
t
h
e
p
r
o
ce
s
s
r
e
g
io
n
m
ar
g
i
n
in
g
.
T
h
e
s
ag
itta
l
i
m
a
g
e
s
eg
m
e
n
tatio
n
to
g
et
ao
r
ta
i
n
a
g
r
a
y
le
v
el
i
m
a
g
e
i
s
d
is
c
u
s
s
ed
in
[
1
4
]
.
I
t
is
a
s
e
m
i
au
to
m
atic
s
eg
m
e
n
tatio
n
p
r
o
ce
s
s
to
s
eg
m
e
n
t
t
h
e
s
a
g
it
t
al
MRI
i
m
a
g
e
b
ase
t
h
at
i
s
c
o
n
n
ec
ted
to
t
h
e
lab
eli
n
g
m
e
t
h
o
d
co
m
p
o
n
en
t
s
.
A
m
et
h
o
d
b
ased
o
n
w
ater
m
ar
k
i
n
g
tec
h
n
iq
u
e
f
o
r
o
b
tain
in
g
t
h
e
i
m
ag
e
o
r
ig
i
n
ali
t
y
i
s
d
is
c
u
s
s
ed
in
[
1
5
]
.
T
h
e
id
en
ti
f
icatio
n
o
f
o
b
j
ec
ts
an
d
th
e
s
m
al
l
ar
ea
o
f
c
h
ic
k
e
n
eg
g
s
ar
e
d
o
n
e
b
y
u
s
i
n
g
t
h
e
b
o
u
n
d
i
n
g
b
o
x
a
n
d
th
e
ce
n
tr
o
id
.
1
.
2
P
ro
blem
Sta
t
e
m
e
nt
a.
T
h
e
m
aj
o
r
h
ar
m
f
u
l
n
e
s
s
an
d
t
h
e
w
ea
k
n
e
s
s
o
f
w
e
ld
in
g
d
ef
ec
t
s
in
th
e
s
teele
d
s
tr
u
c
tu
r
e
ar
e
as
f
o
llo
w
s
:
b.
T
h
e
s
eg
m
en
tatio
n
o
f
t
h
e
w
e
ld
i
m
a
g
e
w
h
o
s
e
in
te
n
s
it
y
an
d
in
-
h
o
m
o
g
e
n
eitie
s
o
f
t
h
e
s
a
m
e
o
b
j
ec
t
ca
n
b
e
d
is
tu
r
b
ed
.
c.
T
h
e
p
r
o
b
lem
o
f
b
o
u
n
d
ar
y
lea
k
ag
e
at
w
ea
k
ed
g
e
s
i
s
a
m
aj
o
r
d
r
aw
b
ac
k
t
h
at
t
h
e
y
r
el
y
m
u
ch
o
n
t
h
e
g
r
ad
ien
t
v
alu
e.
d.
T
h
o
u
g
h
th
e
ar
r
an
g
e
m
e
n
t
s
o
f
u
n
i
f
o
r
m
ill
u
m
i
n
atio
n
ar
e
m
ad
e
v
er
y
co
r
r
ec
tl
y
,
t
h
er
e
i
s
a
v
ib
r
atio
n
o
f
illu
m
i
n
atio
n
o
cc
u
r
r
ed
d
u
r
in
g
t
h
e
w
eld
in
g
p
r
o
ce
s
s
.
1
.
3
T
he
P
ro
po
s
ed
So
lutio
n
T
o
o
v
er
co
m
e
th
e
s
e
p
r
o
b
le
m
s
an
e
f
f
icien
t
C
AD
s
y
s
te
m
f
o
r
w
eld
d
e
f
ec
t
d
etec
tio
n
b
ased
o
n
v
ar
io
u
s
i
m
a
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
e
s
o
n
X
-
r
a
y
w
eld
i
m
ag
e
s
is
p
r
esen
ted
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
co
n
s
is
t
t
h
r
ee
m
ai
n
s
tep
s
lik
e
f
o
r
m
at
io
n
o
f
g
r
ad
ien
t
i
m
ag
e
s
,
f
il
tr
atio
n
b
y
Ga
u
s
s
ian
p
y
r
a
m
id
al
f
ilter
s
alg
o
r
it
h
m
an
d
E
x
p
ec
tatio
n
an
d
Ma
x
i
m
izatio
n
(
E
M)
alg
o
r
ith
m
f
o
r
f
in
al
s
eg
m
e
n
tatio
n
.
T
h
e
p
ap
er
o
r
g
an
izatio
n
is
as
f
o
llo
w
s
:
Sectio
n
2
g
iv
e
s
t
h
e
m
et
h
o
d
s
an
d
m
ater
ial
s
u
s
e
d
f
o
r
th
e
p
r
o
p
o
s
ed
C
A
D
s
y
s
te
m
f
o
r
w
eld
d
ef
ec
ts
d
etec
tio
n
.
T
h
e
n
ex
t
s
ec
tio
n
g
i
v
es
t
h
e
r
esu
lt
s
o
f
th
e
w
eld
d
ef
ec
t
d
etec
tio
n
s
y
s
te
m
an
d
s
ec
t
io
n
4
co
n
clu
d
es t
h
e
C
AD
s
y
s
te
m
.
2.
RE
S
E
ARCH
AND
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
f
o
r
w
el
d
d
ef
ec
t
d
etec
t
io
n
is
co
n
s
id
er
ed
as
an
i
m
ag
e
s
eg
m
e
n
tatio
n
p
r
o
b
lem
.
Fig
u
r
e
1
s
h
o
w
s
t
h
e
f
lo
w
o
f
th
e
C
A
D
s
y
s
te
m
f
o
r
w
eld
d
ef
ec
t
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
9
,
No
.
3
,
Ma
r
ch
2
0
1
8
:
7
6
4
–
7
7
0
766
2
.
1
.
G
ra
dient
I
m
a
g
e
F
o
r
m
a
t
io
n
I
n
th
e
f
ir
s
t
s
tag
e,
t
h
e
i
n
te
n
s
i
t
y
v
ar
iatio
n
(
)
in
b
o
th
h
o
r
izo
n
tal
(
x
)
an
d
v
er
tical
d
ir
ec
tio
n
(
y
)
i
s
co
m
p
u
ted
.
Fo
r
a
2
D
d
i
m
en
s
io
n
al
o
r
i
g
in
al
i
m
a
g
e
d
en
o
ted
b
y
I
,
th
e
i
n
ten
s
it
y
v
ar
iatio
n
i
n
x
an
d
y
d
ir
ec
tio
n
ar
e
g
iv
e
n
b
elo
w
:
)
,
(
)
,
(
y
n
x
I
y
n
x
I
x
(
1
)
)
,
(
)
,
(
n
y
x
I
n
y
x
I
y
(
2
)
w
h
er
e
n
i
s
th
e
s
m
a
lles
t
i
n
te
g
e
r
.
Fro
m
t
h
e
in
ten
s
it
y
v
ar
i
atio
n
s
,
g
r
ad
ie
n
t
m
ag
n
it
u
d
e
i
m
a
g
e
is
cr
ea
ted
w
h
ic
h
s
h
o
w
s
t
h
e
ed
g
es p
r
esen
t in
th
e
o
r
i
g
in
a
l i
m
a
g
e
I
.
T
h
e
g
r
ad
ien
t
m
a
g
n
itu
d
e
i
m
ag
e
G
i
s
co
m
p
u
ted
as
2
2
)
,
(
y
x
y
x
G
(
3
)
Fig
u
r
e
1
.
C
A
D
s
y
s
te
m
f
o
r
w
el
d
d
ef
ec
ts
T
h
e
ab
o
v
e
eq
u
atio
n
is
u
s
ed
to
o
b
tain
th
e
g
r
ad
ien
t
m
a
g
n
itu
d
e
im
a
g
e.
Fig
u
r
e
2
(
a)
s
h
o
w
s
th
e
X
-
r
a
y
w
eld
i
m
ag
e
a
n
d
Fi
g
u
r
e
2
(
b
)
s
h
o
w
s
t
h
e
g
r
ad
ien
t
m
a
g
n
itu
d
e
i
m
ag
e
o
b
tai
n
ed
u
s
i
n
g
(
3
)
.
(
a)
(
b
)
Fig
u
r
e
2
.
(
a)
X
-
r
ay
w
e
ld
i
m
a
g
e
(
b
)
Gr
a
d
ien
t
m
a
g
n
itu
d
e
i
m
a
g
e
I
np
ut
X
-
r
ay
w
el
d
i
m
ag
es
G
r
ad
i
en
t
i
m
a
g
e
f
or
m
atio
n
G
au
ssi
an
py
r
amid
al
f
i
l
t
r
atio
n
E
M
S
eg
m
en
t
a
t
i
on
Fl
a
w
de
t
ected
i
m
ag
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
A
n
N
o
n
Destr
u
ctive
Tes
t
f
o
r
t
h
e
Dete
ct
io
n
o
f W
eld
Defe
cts
…
(
V
.
K
a
la
is
elvi
)
767
2
.
2
.
G
a
us
s
ia
n P
y
ra
m
i
da
l F
iltr
a
t
io
n
I
n
o
r
d
er
t
o
f
in
e
tu
n
e
th
e
ed
g
es
o
b
tain
ed
f
r
o
m
th
e
g
r
ad
ien
t
m
ag
n
it
u
d
e
i
m
a
g
e,
Gau
s
s
ia
n
p
y
r
a
m
id
al
f
ilter
al
g
o
r
ith
m
i
s
e
m
p
lo
y
ed
in
th
e
s
ec
o
n
d
s
ta
g
e.
T
h
e
co
n
c
ep
t
o
f
th
e
Ga
u
s
s
ia
n
p
y
r
a
m
id
r
ep
r
esen
ts
a
m
u
l
ti
-
r
eso
lu
tio
n
s
ce
n
e
w
h
er
e
ea
c
h
f
r
a
m
e
th
a
t
m
a
k
e
s
u
p
a
n
i
m
ag
e
f
lo
w
is
p
r
o
g
r
es
s
i
v
el
y
f
i
lter
ed
an
d
s
u
b
-
s
a
m
p
led
to
ea
s
il
y
d
ea
l
w
it
h
t
h
e
s
ea
r
ch
o
f
o
b
j
ec
ts
at
d
if
f
er
en
t
s
ca
le
s
.
T
h
e
Gau
s
s
ia
n
p
y
r
a
m
id
al
f
ilter
p
r
o
ce
s
s
f
o
r
G(
x
,
y
)
is
as f
o
llo
w
s
:
0
l
l
e
v
e
l
,
f
o
r
,
,
0
y
x
G
y
x
G
P
F
(
4
)
2
2
1
2
2
1
2
,
2
,
,
n
l
m
n
y
m
x
G
P
F
n
m
w
y
x
G
P
F
(
5
)
w
h
er
e
n
m
w
,
is
a
w
e
ig
h
ted
f
u
n
ctio
n
f
o
r
all
id
en
tical
lev
el
s
t
h
at
ar
e
ter
m
ed
as
g
en
er
ati
n
g
th
e
k
er
n
el
p
r
o
p
er
ties
at
lev
el
l+1
.
Fig
u
r
e
3
s
h
o
w
s
t
h
e
ap
p
licatio
n
o
f
Gau
s
s
ia
n
p
y
r
a
m
id
al
f
ilt
r
atio
n
o
n
Gr
ad
ien
t
m
ag
n
it
u
d
e
i
m
ag
e
i
n
Fi
g
u
r
e
2
(
b
)
.
Fig
u
r
e
3
.
Gau
s
s
ian
p
y
r
a
m
id
al
f
ilter
ed
i
m
a
g
e
2
.
3
.
E
M
Seg
m
e
nta
t
io
n
I
n
th
is
s
tag
e,
w
eld
d
ef
ec
ts
ar
e
d
etec
ted
o
r
s
eg
m
e
n
ted
b
y
u
s
i
n
g
E
M
s
e
g
m
en
tat
io
n
alg
o
r
it
h
m
w
it
h
th
e
h
elp
o
f
th
e
f
ilter
ed
i
m
ag
e.
T
h
e
p
r
o
ce
d
u
r
e
f
o
r
E
M
alg
o
r
ith
m
c
lo
s
el
y
f
o
llo
w
s
t
h
e
K
-
m
ea
n
s
clu
s
ter
in
g
alg
o
r
ith
m
.
T
h
e
ac
cu
r
ac
y
o
f
E
M
alg
o
r
ith
m
d
ep
en
d
s
o
n
t
h
e
in
itial
clu
s
ter
v
al
u
es.
L
et
u
s
ass
u
m
e
t
h
at
th
e
s
e
v
alu
e
s
ar
e
v
er
y
clo
s
e
to
t
h
e
g
r
o
u
n
d
tr
u
t
h
d
ata.
A
s
th
e
n
a
m
e
i
m
p
lies
th
e
f
ir
s
t
s
tep
b
eg
i
n
s
with
a
n
E
x
p
ec
tatio
n
s
tep
(
E
)
f
o
r
p
ix
el
z
as in
E
q
n
.
6
.
k
n
n
i
i
i
ij
x
x
p
x
x
p
z
E
1
)
|
(
)
|
(
(
6
)
Usi
n
g
t
h
e
ab
o
v
e
E
q
n
.
6
,
th
e
w
ei
g
h
t
f
o
r
p
ix
el
z
co
n
ce
r
n
i
n
g
p
ar
titi
o
n
j
is
co
m
p
u
ted
.
Fo
r
ea
ch
i
m
ag
e,
th
is
s
tep
co
m
p
u
te
s
w
ei
g
h
t
s
f
o
r
ev
er
y
p
ix
el.
A
f
ter
E
s
tep
,
th
e
m
ax
i
m
iza
tio
n
s
tep
(
M)
b
eg
i
n
s
.
i
m
i
ij
j
x
z
E
m
1
1
(
7
)
Usi
n
g
th
e
ab
o
v
e
E
q
n
.
7
,
t
h
e
w
ei
g
h
t
o
f
j
p
ar
titi
o
n
is
u
p
d
ate
d
.
T
h
en
t
h
e
E
s
tep
i
s
r
ep
ea
ted
u
s
in
g
th
e
n
e
w
s
et
o
f
p
ar
titi
o
n
u
n
til
th
er
e
is
n
o
c
h
a
n
g
e
i
n
t
h
e
p
ar
titi
o
n
v
alu
es.
B
y
u
s
in
g
th
i
s
al
g
o
r
ith
m
,
th
e
f
la
w
s
th
a
t
ar
e
p
r
esen
t
i
n
t
h
e
w
e
ld
i
m
ag
e
ar
e
d
etec
ted
.
F
ig
u
r
e
4
s
h
o
w
s
th
e
f
i
n
al
s
eg
m
e
n
ted
o
u
tp
u
t
i
m
a
g
e
o
b
tain
ed
b
y
E
M
ap
p
r
o
ac
h
f
o
r
th
e
i
m
a
g
e
s
h
o
w
n
in
Fi
g
u
r
e
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
9
,
No
.
3
,
Ma
r
ch
2
0
1
8
:
7
6
4
–
7
7
0
768
Fig
u
r
e
4
.
W
eld
d
ef
ec
t d
etec
tio
n
b
y
E
M
s
e
g
m
e
n
tat
io
n
3.
RE
SU
L
T
AND
DI
SCUS
SI
O
N
I
n
th
i
s
s
t
u
d
y
,
GD
X
-
r
a
y
w
el
d
im
a
g
e
d
atab
ase
[
1
6
]
is
u
s
e
d
to
ev
alu
ate
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
s
y
s
te
m
is
an
al
y
ze
d
r
eg
ar
d
in
g
s
e
n
s
iti
v
it
y
,
s
p
ec
if
icit
y
,
an
d
s
e
g
m
en
ta
tio
n
ac
cu
r
ac
y
u
s
i
n
g
th
e
g
r
o
u
n
d
tr
u
t
h
i
m
a
g
es.
T
h
ese
m
ea
s
u
r
es
ar
e
w
id
el
y
u
s
ed
i
n
m
an
y
i
m
ag
e
p
r
o
ce
s
s
in
g
ap
p
lc
iatio
n
s
[
1
7
-
1
9
]
.
T
h
e
o
u
tp
u
t
i
m
ag
e
o
b
tain
ed
b
y
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
a
n
d
th
e
g
r
o
u
n
d
tr
u
t
h
i
m
a
g
es
t
h
a
t
ar
e
u
s
ed
f
o
r
th
e
p
er
f
o
r
m
a
n
ce
a
n
al
y
s
i
s
ar
e
s
h
o
w
n
i
n
Fi
g
u
r
e
5
.
T
h
e
C
A
D
s
y
s
t
e
m
f
o
r
w
eld
d
e
f
ec
ts
i
s
i
m
p
le
m
en
ted
in
M
A
T
L
AB
R
2
0
1
5
b
.
T
h
e
q
u
alitativ
e
a
n
al
y
s
i
s
f
r
o
m
Fig
u
r
e
5
clea
r
l
y
s
h
o
w
s
th
a
t
t
h
e
p
r
o
p
o
s
ed
C
A
D
s
y
s
te
m
s
eg
m
en
ts
t
h
e
w
eld
d
e
f
ec
ts
f
r
o
m
th
e
o
r
ig
i
n
al
X
-
r
a
y
w
eld
ed
i
m
ag
e
s
i
n
a
n
e
f
f
icie
n
t
m
a
n
n
er
.
I
n
o
r
d
er
to
q
u
an
titati
v
el
y
a
n
al
y
ze
th
e
C
A
D
s
y
s
te
m
,
t
h
e
f
o
llo
w
i
n
g
m
ea
s
u
r
es
;
s
en
s
iti
v
it
y
,
s
p
ec
if
icit
y
an
d
ac
cu
r
ac
y
ar
e
u
s
ed
.
T
h
ese
m
ea
s
u
r
es
ca
n
b
e
ea
s
il
y
o
b
ta
in
ed
f
r
o
m
th
e
co
n
f
u
s
io
n
m
atr
ix
.
I
t i
s
m
ad
e
f
r
o
m
t
h
e
d
ef
ec
t r
eg
io
n
s
(
w
h
ite
p
i
x
els)
a
n
d
n
o
n
-
d
ef
ec
t
r
eg
io
n
s
(
b
lack
p
i
x
els).
(
a
)
(
b)
Fig
u
r
e
5
.
(
a)
Gr
o
u
n
d
tr
u
th
i
m
a
g
e
(
b
)
W
eld
d
ef
ec
t d
etec
tio
n
b
y
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
T
ab
le
1
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
C
A
D
s
y
s
te
m
f
o
r
w
eld
d
ef
ec
t d
etec
tio
n
T
e
st
o
u
t
c
o
me
A
c
t
u
a
l
C
l
a
ss
P
o
si
t
i
v
e
(
w
e
l
d
d
e
f
e
c
t
s)
N
e
g
a
t
i
v
e
(
n
o
n
-
d
e
f
e
c
t
/
g
o
o
d
)
P
o
si
t
i
v
e
(
w
e
l
d
d
e
f
e
c
t
s)
T
r
u
e
P
o
si
t
i
v
e
(
T
P
)
–
W
e
l
d
d
e
f
e
c
t
p
i
x
e
l
i
s c
o
r
r
e
c
t
l
y
i
d
e
n
t
i
f
i
e
d
a
s
d
e
f
e
c
t
e
d
F
a
l
s
e
P
o
si
t
i
v
e
(
F
P
)
–
G
o
o
d
p
i
x
e
l
i
s i
n
c
o
r
r
e
c
t
l
y
i
d
e
n
t
i
f
i
e
d
a
s
w
e
l
d
d
e
f
e
c
t
N
e
g
a
t
i
v
e
(
n
o
n
-
d
e
f
e
c
t
/
g
o
o
d
)
F
a
l
s
e
N
e
g
a
t
i
v
e
(
F
N
)
-
W
e
l
d
d
e
f
e
c
t
p
i
x
e
l
i
s
i
n
c
o
r
r
e
c
t
l
y
i
d
e
n
t
i
f
i
e
d
a
s g
o
o
d
p
i
x
e
l
T
r
u
e
N
e
g
a
t
i
v
e
(
T
N
)
–
G
o
o
d
p
i
x
e
l
i
s c
o
r
r
e
c
t
l
y
c
l
a
ssi
f
i
e
d
a
s g
o
o
d
p
i
x
e
l
Fro
m
th
e
co
n
f
u
s
io
n
m
atr
i
x
,
s
en
s
iti
v
it
y
,
s
p
ec
i
f
icit
y
,
an
d
a
cc
u
r
ac
y
ar
e
co
m
p
u
ted
f
o
r
ea
ch
i
m
ag
e
co
n
ce
r
n
i
n
g
t
h
e
s
e
g
m
en
ted
a
n
d
th
e
g
r
o
u
n
d
tr
u
t
h
i
m
ag
e
s
.
T
h
eir
d
ef
in
itio
n
s
ar
e
as f
o
llo
w
s
:
a.
Sen
s
iti
v
it
y
I
t
tak
es
o
n
l
y
t
h
e
p
o
s
itiv
e
ca
s
e
s
(
w
eld
d
ef
ec
ts
)
.
I
t
is
th
e
r
atio
b
etw
ee
n
th
e
to
tal
T
P
d
ec
is
i
o
n
s
to
th
e
n
u
m
b
er
o
f
ac
tu
a
l p
o
s
itiv
e
ca
s
e
s
.
I
t is d
ef
i
n
ed
b
y
eq
n
.
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
A
n
N
o
n
Destr
u
ctive
Tes
t
f
o
r
t
h
e
Dete
ct
io
n
o
f W
eld
Defe
cts
…
(
V
.
K
a
la
is
elvi
)
769
FN
TP
TP
y
S
e
n
s
i
t
i
v
i
t
(
8
)
b.
Sp
ec
if
icit
y
I
t
d
ea
ls
w
it
h
o
n
l
y
t
h
e
n
e
g
ati
v
e
ca
s
es
(
n
o
n
-
d
ef
ec
t
r
e
g
io
n
s
)
.
I
t
is
th
e
r
atio
b
et
w
ee
n
th
e
to
tal
T
N
d
ec
is
io
n
s
to
th
e
n
u
m
b
er
o
f
ac
t
u
al
n
e
g
ati
v
e
ca
s
e
s
.
I
t i
s
d
ef
i
n
e
d
b
y
E
q
n
.
9
.
TN
FP
TN
y
S
p
e
c
i
f
i
c
i
t
(
9
)
c.
A
cc
u
r
ac
y
I
t
d
ea
ls
w
it
h
b
o
th
p
o
s
iti
v
e
ca
s
es
(
w
eld
d
ef
ec
ts
)
a
n
d
n
eg
at
iv
e
ca
s
es
(
n
o
d
e
f
ec
t
r
e
g
io
n
s
)
.
I
t
is
d
e
f
i
n
ed
b
y
E
q
n
.
1
0
.
TN
FP
FN
TP
TN
TP
A
c
c
u
r
a
c
y
(
1
0
)
T
ab
le
2
s
h
o
w
s
t
h
e
co
m
p
u
ted
p
er
f
o
r
m
a
n
ce
m
ea
s
u
r
es
o
f
t
h
e
s
y
s
te
m
o
n
GD
X
-
r
a
y
i
m
ag
e
d
atab
ase.
A
ll
th
e
i
m
ag
e
s
in
G
D
X
-
r
a
y
i
m
ag
e
d
atab
ase
ar
e
u
s
ed
f
o
r
th
e
ev
a
lu
atio
n
.
T
ab
le
2
.
P
er
f
o
r
m
a
n
ce
o
f
t
h
e
s
y
s
te
m
o
n
GD
X
-
r
a
y
i
m
a
g
e
d
at
ab
ase
d
atab
ase
S
.
N
o
.
A
c
c
u
r
a
c
y
(
%)
S
e
n
si
t
i
v
i
t
y
(
%)
S
p
e
c
i
f
i
c
i
t
y
(
%)
1
8
9
.
6
6
8
9
.
8
9
8
6
.
6
7
2
9
7
.
9
4
9
7
.
9
3
9
9
.
7
5
3
9
9
.
7
3
9
9
.
7
4
9
4
.
7
4
4
9
9
.
4
8
9
9
.
5
1
8
8
.
1
7
5
9
9
.
4
4
9
9
.
4
4
1
0
0
6
9
8
.
8
2
9
8
.
8
3
9
5
.
9
8
7
9
5
.
4
2
9
5
.
7
2
8
7
.
7
3
8
9
9
.
4
8
9
9
.
4
8
1
0
0
9
9
0
.
1
0
8
9
.
6
1
9
8
.
0
3
10
9
8
.
6
2
9
8
.
6
1
1
0
0
A
v
g
9
6
.
8
7
9
6
.
8
8
9
5
.
1
1
Fro
m
T
ab
le
2
,
it
is
o
b
s
er
v
ed
th
at
t
h
e
C
A
D
s
y
s
te
m
d
etec
t
s
9
6
.
8
8
%
o
f
w
eld
d
ef
ec
t
s
an
d
9
5
.
1
1
%
o
f
n
o
n
-
d
ef
ec
t
r
eg
io
n
s
.
A
l
s
o
,
it
p
r
o
v
id
es
an
a
v
er
ag
e
ac
c
u
r
ac
y
o
f
9
6
.
8
7
%
o
n
GD
X
-
r
a
y
i
m
ag
e
d
atab
ase.
T
h
e
m
ea
s
u
r
es
s
en
s
iti
v
it
y
a
n
d
s
p
ec
if
icit
y
s
h
o
w
h
o
w
co
r
r
ec
tl
y
t
h
e
s
eg
m
e
n
ted
o
u
tp
u
t
i
m
ag
e
s
a
r
e
m
atc
h
ed
w
ith
its
g
r
o
u
n
d
tr
u
t
h
i
m
a
g
es.
T
h
e
co
m
p
ar
i
s
o
n
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
t
e
m
i
s
m
ad
e
w
it
h
t
h
e
o
th
er
s
u
cc
ess
f
u
l
w
eld
i
m
a
g
e
s
eg
e
m
e
n
tatio
n
m
et
h
o
d
.
I
t
is
f
o
cu
s
ed
o
n
th
e
d
atab
ase
u
s
ed
an
d
th
e
o
u
tp
u
t
p
ar
a
m
e
t
er
s
lik
e
s
en
s
iti
v
it
y
,
s
p
ec
if
icit
y
a
n
d
th
e
ac
cu
r
ac
y
o
f
t
h
e
s
e
g
m
en
t
a
tio
n
s
y
s
te
m
.
T
ab
le
3
s
h
o
w
s
t
h
e
co
m
p
ar
ati
v
e
an
al
y
s
is
.
I
t
is
clea
r
th
at
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
p
r
o
v
i
d
es b
etter
r
esu
lts
t
h
an
o
t
h
er
s
i
n
ter
m
s
o
f
ac
cu
r
a
y
an
d
s
e
n
s
i
ti
v
it
y
.
T
ab
le
3
.
C
o
m
p
ar
is
io
n
o
f
p
r
o
p
o
s
ed
w
eld
i
m
a
g
e
s
e
g
m
en
tatio
n
w
it
h
o
th
er
m
e
th
o
d
s
D
a
t
a
b
a
se
T
e
c
h
n
i
q
u
e
u
se
d
S
e
n
si
t
i
v
i
t
y
S
p
e
c
i
f
i
c
i
t
y
A
c
c
u
r
a
c
y
G
D
X
-
r
a
y
s
P
C
A
b
a
se
d
S
V
M
mo
d
e
l
[
2
0
]
8
7
.
2
8
9
6
.
3
1
9
0
.
7
5
G
D
X
-
r
a
y
s
Off
-
C
e
n
t
e
r
S
a
l
i
e
n
c
y
M
a
p
C
o
m
p
u
t
a
t
i
o
n
w
i
t
h
L
e
v
e
l
S
e
t
A
c
t
i
v
e
C
o
n
t
o
u
r
En
e
r
g
y
F
o
r
mu
l
a
t
i
o
n
[
2
1
]
-
-
8
7
%
G
D
X
-
r
a
y
s
R
a
d
i
o
g
r
a
p
h
i
c
p
a
t
t
e
r
n
s
b
a
se
d
g
e
o
me
t
r
i
c
f
e
a
t
u
r
e
s a
n
d
N
e
u
r
a
l
n
e
t
w
o
r
k
c
l
a
ssi
f
i
e
r
[
2
2
]
8
3
.
9
7
4
.
8
8
0
.
6
G
D
X
-
r
a
y
s
P
r
o
p
o
se
d
me
t
h
o
d
9
6
.
8
8
9
5
.
1
1
9
6
.
8
8
4.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
er
,
a
n
o
n
-
d
estr
u
cti
v
e
test
m
e
th
o
d
f
o
r
th
e
d
etec
tio
n
o
f
th
e
w
eld
in
g
d
ef
ec
t
s
is
p
r
o
p
o
s
ed
u
s
i
n
g
X
-
r
a
y
i
m
a
g
es.
T
h
e
w
e
ld
d
ef
ec
ts
r
ed
u
ce
t
h
e
q
u
ali
t
y
o
f
t
h
e
m
a
ter
ials
.
As
th
e
y
ar
e
n
o
t
v
is
ib
le
to
th
e
n
ak
ed
e
y
e,
it r
eq
u
ir
es a
C
A
D
s
y
s
te
m
to
id
en
tify
t
h
e
w
eld
d
ef
ec
t
s
.
T
h
e
id
en
ti
f
icat
io
n
o
f
w
eld
d
ef
ec
ts
is
d
o
n
e
b
y
u
s
in
g
th
e
t
h
r
ee
s
tag
e
s
;
g
r
ad
ien
t
i
m
ag
e
f
o
r
m
a
tio
n
,
f
iltra
tio
n
b
y
Ga
u
s
s
ia
n
p
y
r
a
m
i
d
al
f
i
lt
er
alg
o
r
ith
m
,
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
9
,
No
.
3
,
Ma
r
ch
2
0
1
8
:
7
6
4
–
7
7
0
770
s
eg
m
e
n
tatio
n
b
y
E
M
s
e
g
m
e
n
tatio
n
al
g
o
r
ith
m
.
R
e
s
u
lts
s
h
o
w
t
h
at
t
h
e
C
A
D
s
y
s
te
m
p
r
o
v
id
es
9
6
.
8
8
%
(
s
en
s
i
tiv
it
y
)
,
9
5
.
1
1
% (
s
p
ec
if
icit
y
)
,
an
d
an
a
v
er
ag
e
ac
c
u
r
ac
y
o
f
9
6
.
8
7
% o
n
GD
X
-
r
a
y
i
m
ag
e
d
atab
ase.
RE
F
E
R
E
NC
E
S
[1
]
W
a
n
g
Z.
Au
to
ma
ti
c
S
e
g
me
n
t
a
ti
o
n
o
f
F
u
zz
y
L
a
se
r
L
i
n
e
s
wit
h
S
u
b
-
Pi
x
e
l
Acc
u
ra
c
y
fro
m
th
e
Un
e
v
e
n
Ba
c
k
g
ro
u
n
d
d
u
rin
g
Ro
b
o
t
ic A
rc
W
e
ld
in
g
.
IEE
E
7
th
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
In
telli
g
e
n
t
S
y
ste
m
s,
M
o
d
e
li
n
g
a
n
d
S
im
u
latio
n
.
2
0
1
6
;
1
5
7
-
1
6
2
.
[2
]
Kim
C,
H
a
n
DS,
Kim
JK
,
Ki
m
BI.
Au
to
ma
ti
c
d
e
tec
ti
o
n
o
f
d
e
fec
ti
v
e
we
ld
in
g
e
lec
tro
d
e
ti
p
s
u
sin
g
c
o
lo
u
r
se
g
me
n
ta
ti
o
n
a
n
d
Ho
u
g
h
c
irc
le d
e
tec
ti
o
n
.
IEE
E
Re
g
io
n
10
th
C
o
n
f
e
re
n
c
e
.
2
0
1
6
;
1
3
7
1
-
1
3
7
4
.
[3
]
Da
n
g
C,
G
a
o
J,
W
a
n
g
Z,
Ch
e
n
F
,
X
iao
Y.
M
u
lt
i
-
ste
p
ra
d
i
o
g
ra
p
h
ic
ima
g
e
e
n
h
a
n
c
e
me
n
t
c
o
n
f
o
rm
in
g
to
we
ld
d
e
fec
t
se
g
me
n
ta
ti
o
n
.
I
ET
Im
a
g
e
P
ro
c
e
ss
in
g
.
2
0
1
5
;
9
(1
1
):
9
4
3
-
9
5
0
.
[4
]
S
u
n
d
a
ra
m
M
,
Jo
se
JP
,
Ja
ff
in
o
G
.
W
e
ld
in
g
d
e
fec
ts
e
x
tra
c
ti
o
n
fo
r
r
a
d
i
o
g
r
a
p
h
ic
ima
g
e
s
u
s
in
g
C
-
me
a
n
s
se
g
me
n
ta
ti
o
n
me
th
o
d
.
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Co
m
m
u
n
ica
ti
o
n
a
n
d
Ne
tw
o
rk
T
e
c
h
n
o
l
o
g
ies
.
2
0
1
4
;
79
-
83.
[5
]
L
iao
Z,
S
u
n
J.
Im
a
g
e
s
e
g
m
e
n
tatio
n
i
n
w
e
ld
d
e
f
e
c
t
d
e
tec
ti
o
n
b
a
se
d
o
n
m
o
d
if
ied
b
a
c
k
g
ro
u
n
d
su
b
trac
ti
o
n
.
IEE
E
6
t
h
In
tern
a
ti
o
n
a
l
C
o
n
g
re
ss
o
n
Im
a
g
e
a
n
d
S
ig
n
a
l
P
ro
c
e
ss
in
g
.
2
0
1
3
;
2
:
6
1
0
-
6
1
5
.
[6
]
G
o
u
m
e
id
a
n
e
A
B,
Kh
a
m
a
d
ja
M
.
M
e
rg
in
g
d
isc
re
p
a
n
c
y
me
a
su
re
s
fo
r
re
g
io
n
-
b
a
se
d
se
g
me
n
t
a
t
i
o
n
re
su
lt
s
e
v
a
lu
a
ti
o
n
a
n
d
c
o
mp
a
riso
n
:
A
p
p
l
ica
ti
o
n
to
t
h
re
sh
o
ld
e
d
we
ld
d
e
fec
t
ra
d
i
o
g
ra
p
h
ic
ima
g
e
s.
IEE
E
8
th
In
tern
a
ti
o
n
a
l
S
y
m
p
o
siu
m
o
n
Im
a
g
e
a
n
d
S
ig
n
a
l
P
ro
c
e
ss
in
g
a
n
d
A
n
a
ly
sis.
2
0
1
3
;
78
-
8
2
.
[7
]
L
iu
X
.
Im
a
g
e
p
r
o
c
e
ss
in
g
i
n
we
ld
se
a
m
tra
c
k
in
g
wi
th
l
a
se
r
v
isio
n
b
a
se
d
o
n
r
a
d
o
n
tr
a
n
sf
o
rm
a
n
d
F
CM
c
lu
ste
rin
g
se
g
me
n
ta
ti
o
n
.
IE
EE
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
In
telli
g
e
n
t
C
o
m
p
u
tatio
n
T
e
c
h
n
o
lo
g
y
a
n
d
A
u
to
m
a
ti
o
n
.
2
0
1
0
;
2
:
470
-
4
7
3
.
[8
]
Jia
J,
L
i
H,
Jia
Z.
Ima
g
e
se
g
m
e
n
ta
ti
o
n
o
f
th
e
u
n
d
e
rwa
ter
we
l
d
in
g
V
-
se
a
m
ima
g
e
b
a
se
d
o
n
i
mp
ro
v
e
d
tw
o
-
d
ime
n
sio
n
a
l
Otsu
a
lg
o
rith
m
.
IE
EE
6
th
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
F
u
z
z
y
S
y
ste
m
s
a
n
d
Kn
o
w
led
g
e
Disc
o
v
e
r
y
.
2
0
0
9
;
5
:
3
9
7
-
4
0
0
.
[9
]
M
a
h
m
o
u
d
i
A
,
Re
g
r
a
g
u
i
F
.
W
e
ld
in
g
d
e
fec
t
d
e
tec
ti
o
n
b
y
se
g
me
n
ta
ti
o
n
o
f
ra
d
i
o
g
ra
p
h
ic
ima
g
e
s
.
IEE
E
W
RI
W
o
rld
Co
n
g
re
ss
o
n
C
o
m
p
u
ter S
c
ien
c
e
a
n
d
I
n
f
o
rm
a
ti
o
n
En
g
in
e
e
rin
g
.
2
0
0
9
;
7
:
1
1
1
-
1
1
5
.
[1
0
]
M
a
h
m
o
u
d
i
A
,
Re
g
ra
g
u
i
F
.
Fa
st
se
g
me
n
ta
ti
o
n
me
t
h
o
d
fo
r
d
e
fec
ts
d
e
tec
ti
o
n
i
n
ra
d
io
g
ra
p
h
ic
im
a
g
e
s
o
f
we
ld
s
.
IEE
E/
A
CS
In
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
ter S
y
ste
m
s an
d
A
p
p
li
c
a
ti
o
n
s.
2
0
0
9
;
8
5
7
-
8
6
0
.
[1
1
]
G
h
a
rsa
ll
a
h
M
B,
Br
a
iek
EB.
Ima
g
e
se
g
me
n
ta
t
io
n
f
o
r
d
e
fec
t
d
e
tec
ti
o
n
b
a
se
d
o
n
lev
e
l
se
t
a
c
ti
v
e
c
o
n
t
o
u
r
c
o
m
b
in
e
d
wit
h
sa
l
ien
c
y
ma
p
.
IEE
E
16
th
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
c
ien
c
e
s
a
n
d
T
e
c
h
n
iq
u
e
s
o
f
A
u
to
m
a
ti
c
Co
n
tr
o
l
a
n
d
Co
m
p
u
ter E
n
g
in
e
e
rin
g
.
2
0
1
5
;
388
-
3
9
2
.
[1
2
]
Zh
a
n
g
S
,
Zh
a
n
g
Y,
Ya
n
g
T
,
Jin
C,
S
h
a
n
g
G
.
Res
e
a
rc
h
o
n
L
ED
f
il
a
me
n
t
s
p
o
t
we
ld
i
n
g
ro
b
o
t
b
a
se
d
o
n
m
a
c
h
in
e
v
isio
n
.
I
EE
E
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
ti
o
n
a
n
d
A
u
to
m
a
ti
o
n
.
2
0
1
6
;
1
5
1
0
-
1
5
1
4
.
[1
3
]
Zh
a
n
g
J,
X
ie
C,
S
o
n
g
L
,
L
i
R,
Ch
e
n
H.
Ro
b
u
st
Im
a
g
e
S
e
g
m
e
n
tatio
n
Us
in
g
L
BP
Em
b
e
d
d
e
d
Re
g
io
n
M
e
rg
in
g
.
T
EL
KOM
NIKA
(
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l)
.
2
0
1
6
;
14
(
1
):
3
6
8
-
3
7
7
.
[1
4
]
Rim
in
a
rsih
D,
Ka
r
y
a
ti
CM
,
M
u
ti
a
ra
A
B,
Wah
y
u
d
i
B,
Er
n
a
stu
ti
E.
M
RI
S
a
g
it
tal
Im
a
g
e
S
e
g
m
e
n
tatio
n
f
ro
m
P
a
ti
e
n
ts
w
it
h
A
b
d
o
m
in
a
l
A
o
rti
c
A
n
e
u
r
y
s
m
s
.
T
EL
KOM
NIKA
(
T
e
le
c
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
E
lec
tro
n
ics
a
n
d
Co
n
tro
l)
.
2
0
1
6
;
1
4
(3
):
1
1
0
5
-
1
1
1
2
.
[1
5
]
Yu
d
h
a
n
a
A
,
S
u
n
a
rd
i
S
,
S
a
if
u
l
lah
S
.
S
e
g
m
e
n
tatio
n
Co
m
p
a
rin
g
Eg
g
s
W
a
ter
m
a
rk
in
g
I
m
a
g
e
a
n
d
Orig
in
a
l
Im
a
g
e
.
Bu
ll
e
ti
n
o
f
El
e
c
trica
l
E
n
g
i
n
e
e
rin
g
a
n
d
In
fo
rm
a
t
ics
.
2
0
1
7
;
6
(
1
):
4
7
-
5
3
.
[1
6
]
G
D X
-
ra
y
i
m
a
g
e
d
a
tab
a
se
:
h
tt
p
:/
/
d
m
e
r
y
.
in
g
.
p
u
c
.
c
l/
in
d
e
x
.
p
h
p
/m
a
teria
l/
g
d
x
ra
y
/
[1
7
]
S
o
n
a
w
a
n
e
JM,
G
a
ik
wa
d
S
D,
P
ra
k
a
sh
G
.
M
ic
ro
a
rr
a
y
d
a
ta
c
l
a
ss
if
i
c
a
ti
o
n
u
si
n
g
d
u
a
l
tre
e
m
-
b
a
n
d
w
a
v
e
let
fea
tu
re
s
.
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
A
d
v
a
n
c
e
s
in
S
ig
n
a
l
a
n
d
Im
a
g
e
S
c
ien
c
e
s.
2
0
1
7
;
3
(1
)
:
1
9
-
2
4
.
[1
8
]
V
ij
a
y
a
A
rju
n
a
n
R.
ECG
S
ig
n
a
l
C
las
sif
ic
a
ti
o
n
Ba
se
d
o
n
S
tatisti
c
a
l
F
e
a
tu
re
s
w
it
h
S
v
m
Clas
si
f
ica
ti
o
n
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
s in
S
i
g
n
a
l
a
n
d
Ima
g
e
S
c
ien
c
e
s
.
2
0
1
6
;
2
(1
):
5
-
1
0
.
[1
9
]
S
o
n
i
a
R.
M
e
lan
o
m
a
I
m
a
g
e
Cl
a
ss
if
ic
a
ti
o
n
S
y
ste
m
b
y
NSCT
F
e
a
tu
re
s
a
n
d
Ba
y
e
s
Clas
sif
i
c
a
ti
o
n
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
s in
S
i
g
n
a
l
a
n
d
Ima
g
e
S
c
ien
c
e
s
.
2
0
1
6
;
2
(2
):
2
7
-
33.
[2
0
]
M
u
W
,
G
a
o
J,
Jia
n
g
H,
W
a
n
g
Z,
Ch
e
n
F
,
Da
n
g
C.
Au
to
ma
ti
c
c
la
ss
if
ica
ti
o
n
a
p
p
r
o
a
c
h
to
we
l
d
d
e
f
e
c
ts
b
a
se
d
o
n
PCA
a
n
d
S
VM
.
I
n
sig
h
t
-
No
n
-
De
stru
c
ti
v
e
T
e
stin
g
a
n
d
Co
n
d
it
i
o
n
M
o
n
it
o
ri
n
g
.
2
0
1
3
;
5
5
(
1
0
)
:
5
3
5
-
5
3
9
.
[2
1
]
Be
n
G
h
a
rsa
ll
a
h
M
,
Be
n
Bra
iek
E.
W
e
ld
in
sp
e
c
ti
o
n
b
a
se
d
o
n
ra
d
io
g
ra
p
h
y
i
m
a
g
e
se
g
m
e
n
tatio
n
w
it
h
lev
e
l
se
t
a
c
ti
v
e
c
o
n
to
u
r
g
u
i
d
e
d
o
f
f
-
c
e
n
ter sa
li
e
n
c
y
map
.
Ad
v
a
n
c
e
s i
n
M
a
ter
ia
ls
S
c
i
e
n
c
e
a
n
d
En
g
in
e
e
rin
g
.
2
0
1
5
;
1
-
1
0
.
[2
2
]
d
a
S
il
v
a
RR,
S
iq
u
e
ira
M
H,
d
e
S
o
u
z
a
M
P
V
,
Re
b
e
ll
o
JM,
Ca
lo
b
a
L
P
.
Esti
m
a
ted
a
c
c
u
ra
c
y
o
f
c
l
a
ss
if
ic
a
ti
o
n
o
f
d
e
f
e
c
ts
d
e
tec
ted
in
w
e
ld
e
d
jo
in
ts
b
y
ra
d
io
g
ra
p
h
ic t
e
sts.
NDT
&
e
In
ter
n
a
ti
o
n
a
l
.
2
0
0
5
;
3
8
(5
):
3
3
5
-
3
4
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.